Spatial Contrastive Learning for Few-Shot Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Spatial Contrastive Learning for Few-Shot Classification

Résumé

In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable features. In particular, we present a novel attention-based spatial contrastive objective to learn locally discriminative and class-agnostic features. As a result, our approach overcomes some of the limitations of the cross-entropy loss, such as its excessive discrimination towards seen classes, which reduces the transferability of features to unseen classes. With extensive experiments, we show that the proposed method outperforms state-of-the-art approaches, confirming the importance of learning good and transferable embeddings for few-shot learning Code: https://github.com/yassouali/SCL.
Fichier principal
Vignette du fichier
2012.13831.pdf (2.66 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04327293 , version 1 (06-12-2023)

Identifiants

Citer

Yassine Ouali, Céline Hudelot, Myriam Tami. Spatial Contrastive Learning for Few-Shot Classification. ECML, 2021, Bilbao, Spain. ⟨10.1007/978-3-030-86486-6_41⟩. ⟨hal-04327293⟩
9 Consultations
5 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More